im-reminder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input to define the
messagefield within scheduled job payloads, which are then triggered as agent turns. \n - Ingestion points: User instructions for reminder creation (detailed in
SKILL.md). \n - Boundary markers: No specific delimiters or safety instructions are used to wrap user-provided text within the scheduled message payload. \n
- Capability inventory: Capability to schedule future agent actions and deliver messages to external IM channels via the
agentTurnpayload kind. \n - Sanitization: No documented sanitization or filtering of the user-provided message content before it is stored in the job configuration.
Audit Metadata